Junhua Mao

Computer Vision and Pattern Recognition · 2014–2016

A researcher in the Science corpus: 8 papers; trusts 1,007 researchers and is trusted by 2,788 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 205 citations into it; #719 of 21,575 by trust here, #884 by citations
• Artificial Intelligence — 174 citations into it; #921 of 35,345 by trust here, #1,107 by citations
• Natural Language Processing — 105 citations into it; #929 of 5,688 by trust here, #516 by citations
• Multimodal Learning — 90 citations into it; #49 of 1,211 by trust here, #102 by citations
• Model Architectures — 50 citations into it; #1,545 of 2,278 by trust here, #1,038 by citations
• Evaluation & Benchmarks — 45 citations into it
• Representation & Self-Supervised Learning — 26 citations into it
• Large Language Models — 14 citations into it

Whom Junhua Mao trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Geoffrey E. Hinton
2. Alex Krizhevsky
3. Ilya Sutskever
4. Karen Simonyan
5. Yoshua Bengio
6. Tomas Mikolov
7. Ross B. Girshick
8. Ruslan Salakhutdinov
9. Oriol Vinyals
10. Yann LeCun

Who trusts Junhua Mao overall

1. Qi Wu
2. Marcus Rohrbach
3. Zhe Gan
4. Ronghang Hu
5. Xinlei Chen
6. Trevor Darrell
7. Jiasen Lu
8. Chunhua Shen
9. Lisa Anne Hendricks
10. Yi Yang

Papers from Junhua Mao's perspective

Ordered by how strongly the researchers Junhua Mao trusts endorse each paper. Same corpus, a different order for every researcher.

1. ImageNet classification with deep convolutional neural networks
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Long Short-Term Memory
5. Attention is All you Need (Neural Information Processing Systems)
6. ImageNet: A large-scale hierarchical image database
7. Gradient-based learning applied to document recognition
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. ImageNet Large Scale Visual Recognition Challenge
10. Going deeper with convolutions

Their papers

• Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN) (2014) — 1,283 citations
• Generation and Comprehension of Unambiguous Object Descriptions (2015) — 1,750 citations
• Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question (2015) — 531 citations
• Explain Images with Multimodal Recurrent Neural Networks (2014) — 405 citations
• Learning Like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Images (2015) — 161 citations
• Attention Correctness in Neural Image Captioning (2016) — 229 citations
• CNN-RNN: A Unified Framework for Multi-label Image Classification (2016) — 1,254 citations
• Training and Evaluating Multimodal Word Embeddings with Large-scale Web Annotated Images (2016) — 51 citations